Topic
Everything filed under AI, newest first.
RSS · JSON · All topics
Helping build shared standards for advanced AI
OpenAI argues for U.S.-led shared technical standards for frontier AI—including evaluation, incident reporting, and cautious treatment of recursive self-improvement—via the Appia Foundation.
3 min · 708 words
The National Design Studio open sources Rampart, a 14.7 MB on-device PII filter for AI chat that runs in the browser. It pairs validated regular expressions for structured data like SSNs and card numbers with a small MiniLM model for names and addresses, and reports 98.4% private-term recall across seven languages.
4 min · 841 words
Reviewing code in the agent era
Reviewing code in the agent era Last week we launched Diffs, a new way to review PRs directly inside Linear. Since then we’ve had a lot of questions about it, so we wanted to share more about why we built the feature and how we use it ourselves today. Like a lot of people who build software, I f...
4 min · 870 words
"Vibe coding" is the new "Internet dating"
An analogy between early-2000s internet dating stigma and today's vibe-coding skepticism: both start as jokes, then quietly become how a lot of people actually meet their goals.
1 min · 199 words
Building a Multi-Agent System from Scratch: Architecture Patterns
Kadharmoideen Fadurudeen walks through orchestrator-worker, blackboard and pipeline patterns for coordinating multiple AI agents, and the failure modes that appear once a system grows past a single-agent demo.
7 min · 1,550 words
AI-generated posters don’t have to be horribleA practical workflow for event posters that don’t look like every other AI flyer
John Hartnup shows how to stop AI event posters looking identical: constrain composition, type, and color with concrete prompts and layout rules so the result still looks designed rather than generically generated.
6 min · 1,414 words
AI is killing All About Berlin
Nicolas Bouliane describes how All About Berlin, the website he has run since 2017 and lived from since 2020, lost about 75% of its traffic to Google AI Overviews after seven years of growth, and argues AI trained on his work is now putting him out of work.
2 min · 419 words
Co-Scientist: A multi-agent AI partner to accelerate research
Google DeepMind introduces Co-Scientist, a Gemini-based multi-agent system that generates, debates, and evolves scientific hypotheses, with lab collaborations and a Hypothesis Generation rollout for researchers.
5 min · 1,131 words
Addy Osmani distinguishes cognitive offloading (delegating to AI while still owning the answer) from cognitive surrender (accepting AI output wholesale), drawing on Wharton research by Shaw and Nave, and offers habits for engineers to avoid accumulating comprehension debt when coding with agents.
11 min · 2,432 words
AI Now Writes as Many Online Articles as HumansGraphite’s Common Crawl sample finds primarily AI-generated articles plateaued near 50%
Graphite’s Five Percent research averages three AI detectors across tens of thousands of English articles and finds primarily AI-generated pieces have plateaued near half of new articles since early 2025—after a steep rise following ChatGPT’s launch.
8 min · 1,859 words
A working manifesto by Briana (Mazzio) May on what humans bring now that models are very good: breaking rules on purpose, finding inspiration in weird places, and advocating for the human on the other end of the work.
4 min · 1,006 words
Put a price on research breakthroughs
Alex Wang argues that AI neolabs are being asked to pull off two moonshots at once, a research breakthrough and a venture-scale business, and proposes a pharma-style model where frontier labs put explicit prices on breakthroughs such as cheaper training runs so neolabs can focus on research and sell or be acquired.
8 min · 1,767 words
Giving Your Home AI Agent Real Tools: MCP Servers on a Mac mini M6
A walkthrough of the MCP servers James M runs on a Mac mini M6—filesystem, email, calendar, notes, home automation—and the permission choices that keep an always-on home agent from becoming a liability.
8 min · 1,743 words
The fall of the theorem economyHow AI could destroy mathematics and barely touch it
David Bessis argues AI is exploiting mathematicians' honor-code incentives: when theorems become cheap to produce, prestige-driven theorem economies collapse even if mathematical understanding itself is barely touched.
47 min · 10,783 words
We Audited 10 Popular Open-Source Robot Datasets. Here's What We Found.
Traceplane ran automated quality checks on ten widely used open robotics datasets and found structural or semantic issues in every one—arguing trajectory data needs ingest-time QA like every other data-intensive field.
11 min · 2,503 words
The LISP curse, now coming to your ecosystem!
An essay arguing that LLM-assisted coding could spread the "LISP curse" to every ecosystem: when generating bespoke code is easy, developers work in isolation and open source collaboration on shared libraries may decline.
3 min · 623 words
AI Isn't Replacing SREs. It's Deskilling Them.
Elizabeth of SigNoz argues that AI is not replacing site reliability engineers but quietly eroding their skills: by automating the routine 95% of incident work, it removes the practice SREs need to stay sharp for the rare, novel 5% of failures where human judgment matters most, and suggests ways teams can keep engineers engaged.
7 min · 1,625 words
Harness engineering: leveraging Codex in an agent-first world
OpenAI engineer Ryan Lopopolo on harness engineering: how Codex and agent-first workflows reshape the scaffolding around models, from prompts and tools to evaluation and production loops.
13 min · 3,025 words
Software is still about thinking
Cursor’s head of design argues AI coding creates an illusion of speed without structure: unclear systems thinking now produces slop at scale, while clear architecture compounds into 100x leverage.
2 min · 468 words
Minions: Stripe’s one-shot, end-to-end coding agentsUnattended coding agents that produce more than a thousand merged PRs a week at Stripe.
Stripe’s Minions are fully unattended coding agents that one-shot tasks end-to-end. Humans review the PRs; the agents write the code—here’s how the harness works.
7 min · 1,510 words